Online Active Perception for Partially Observable Markov Decision Processes with Limited Budget.
Mahsa GhasemiUfuk TopcuPublished in: CDC (2019)
Keyphrases
- limited budget
- partially observable markov decision processes
- planning under uncertainty
- finite state
- belief state
- partially observable domains
- belief space
- reinforcement learning
- dynamical systems
- partially observable markov
- partially observable stochastic games
- decision problems
- markov decision processes
- stochastic domains
- optimal policy
- planning problems
- weighted distance
- heuristic search
- np hard
- multi agent